Reinforcement learning algorithms that use eligibility traces, such as Sarsa(λ), have been empirically shown to be effective in learning good estimated-state-based policies in pa...
An approach to handle the complex dynamics of a multi-agent system is based on distinguishing aggregation levels by structuring the system into parts or components. The behavior of...
Thispaper describesAPE(the Atlas PlanningEngine),the reactive planner at the center of the Atlas dialogue managementsystem. The goal of Atlas is to build conversation-basedsystems...
First step in developing electronic book is to build a conceptual model. The model described in this paper is designed by integrating Multiple Intelligences Theory with existing el...
Assistant Agents help ordinary people about computer tasks, in many ways, thanks to their rational reasoning capabilities about the current model of the world. However they face st...